Model Context Protocol (MCP) is an open standard for providing context to generative AI applications. In this tutorial, you’ll build your first MCP server in Python using open‑source SDKs and development tools.
We’ll begin with a brief overview of MCP concepts and how servers and clients communicate. From there, you’ll implement a local MCP server in Python, define tools, and interact with them using AI agents.
Once the basics are in place, we’ll add essential real‑world features, including authentication. You’ll learn how to secure an MCP server using open‑source, OAuth‑compatible authentication providers and understand how authentication fits into the MCP request flow.
This tutorial is hands‑on: participants will write and run Python code throughout the session and leave with a working MCP server they can extend after the conference.